Questions tagged [static-quantization]
5 questions
1
vote
0 answers
Is there any method to convert a quantization aware pytorch model to .tflite?
I have trained yolov4-tiny on pytorch with quantization aware training. My model layers look…
Abhishek Negi
- 11
- 1
1
vote
2 answers
Any idea of to solve the version problem of PyTorch model on android device? The model version must be between 3 and 5But the model version is 7
I am getting the following error while running a PyTorch model on android model?
Lite Interpreter verson number does not match. The model version must be between 3 and 5But the model version is 7 ()
Any suggestion?
Celik
- 2,311
- 2
- 32
- 54
0
votes
1 answer
Is it possible to perform quantization on densenet169 and how?
I have been trying to performing quantization on a densenet model without success. I have been trying to implement pytorch post training static quantization. Pytorch has quantized versions of other models, but does not have for densenet. Is it…
Cyril
- 1
- 1
0
votes
1 answer
Why are some nn.Linear layers not quantized by Pytorch?
I'm quantizing the Swin transformer (static PTQ) using the following function:
def static_quantize(m, data_loader):
backend = 'qnnpack'
torch.backends.quantized.engine = backend
m.eval()
m.qconfig =…
corazza
- 31,222
- 37
- 115
- 186
0
votes
1 answer
Why did I get 'AssertionError: did not find fuser method for:' error while doing static quantization for a PyTorch model
I am getting the following error while I am trying to apply static quantization on a model. The error is in the fuse part of the code: torch.quantization.fuse_modules(model, modules_to_fuse):
model = torch.quantization.fuse_modules(model,…
Celik
- 2,311
- 2
- 32
- 54